多目标优化
数学优化
帕累托原理
计算机科学
优化测试函数
最优化问题
趋同(经济学)
空格(标点符号)
进化算法
分布估计算法
决策者
多群优化
数学
运筹学
经济
操作系统
经济增长
作者
Jing Liang,Caitong Yue,Boyang Qu
出处
期刊:
[Institute of Electrical and Electronics Engineers]
日期:2016-07-01
卷期号:: 2454-2461
被引量:330
标识
DOI:10.1109/cec.2016.7744093
摘要
In real world applications, there are many multi-objective optimization problems. Most existing multi-objective optimization algorithms focus on improving the diversity, spread and convergence of the solutions in the objective space. Few works study the distribution of solutions in the decision space. In practical applications, some multi-objective problems have different Pareto sets with the same objective values and these problems are defined as multimodal multi-objective optimization problems. It is of great significance to provide all the Pareto sets for the decision maker. This paper describes the concept of multimodal multi-objective optimization problems in detail. Novel test functions are also designed to judge the performance of different algorithms. Moreover, some existing multi-objective algorithms are tested and compared. Finally, a decision space based niching multi-objective evolutionary algorithm is proposed to solve these problems. The experimental results suggest that existing multi-objective optimization algorithms fail to find all the Pareto sets while the proposed algorithm is able to find almost all the Pareto sets without deteriorating the distribution of solutions in the objective space.
科研通智能强力驱动
Strongly Powered by AbleSci AI